Shot Transition Detection with Minimal Decoding of MPEG Video Streams

Authors: Mona A. Fouad, Fatma M. Bayoumi, Hoda M. Onsi, Mohamed G. Darwish

Abstract:

Digital libraries become more and more necessary in order to support users with powerful and easy-to-use tools for searching, browsing and retrieving media information. The starting point for these tasks is the segmentation of video content into shots. To segment MPEG video streams into shots, a fully automatic procedure to detect both abrupt and gradual transitions (dissolve and fade-groups) with minimal decoding in real time is developed in this study. Each was explored through two phases: macro-block type's analysis in B-frames, and on-demand intensity information analysis. The experimental results show remarkable performance in detecting gradual transitions of some kinds of input data and comparable results of the rest of the examined video streams. Almost all abrupt transitions could be detected with very few false positive alarms.

Keywords: Adaptive threshold, abrupt transitions, gradual transitions, MPEG video streams.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1086187

References:

[1] R. Lienhart, "Reliable Transition Detection in Videos: A Survey and Practitioner-s Guide," International Journal of Image and Graphics, 1(3):469-486, July 2001.
[2] I. Koprinska and S. Carrato, "Temporal video segmentation: a survey," Signal Processing: Image Communication 16(5):477-500, January 2001.
[3] U. Gargi, R. R. Kasturi, and S. H. Strayer, "Performance Characterization of Video-Shot-Change Detection Methods," IEEE Transactions on Circuits and Systems for Video Technology, vol. 10, No. 1, February 2000.
[4] S. Lee and M. H. Hayes, "Scene Change Detection Using Adaptive Threshold and Sub-Macro-block Images in Compressed Sequences," IEEE International Conference on Multimedia and Expo, 2001.
[5] J. Calic and E. Izquierdo, "Towards Real-Time Shot Detection in the Mpeg-Compressed Domain," Proceedings of WIAMIS'2001 - Workshop on Image Analysis for Multimedia Interactive Services, Tempera, Finland, May 2001.
[6] C. Doulaverakis, S. Vagionitis, Michalis Zervakis, and Euripides G. M. Petrakis, "Adaptive Methods for Motion Characterization and Segmentation of MPEG Compressed Frame Sequences," ICIAR (1) 2004: 310-317
[7] H. Koumaras,a G. Gardikis,b G. Xilouris,a E. Pallis,c and A. Kourtis, "Shot boundary detection without threshold parameters," 2006 SPIE and IS&T.
[8] D. LeGall, J. L Mitchell, W. B. Pennbaker, and C. E. Fogg, "MPEG video compression standard", Chapman & Hall, New York, USA, 1996.
[9] H.J. Zhang, A. Kankanhali, and S.W. Smoliar, "Automatic Partitioning of Full Motion Video. Multimedia Systems," 1993.
[10] S. Lefevre, J. Holler and N. Vincent, "Real-time Temporal Segmentation of Compressed and Uncompressed Dynamic Color image Sequences," International Workshop on Real Time Image Sequence Analysis, pages 56-62, Oulu, Finland, August 2000.